© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19131
    Prev
    Next
    INDEX
    Explanations

    Course descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _initial
    -0.09
    	initial
    -0.09
    (initial
    -0.09
     constrained
    -0.08
    (configuration
    -0.08
    /functions
    -0.08
    ்களின்
    -0.08
    /questions
    -0.08
    ുകളുടെ
    -0.08
    rophic
    -0.08
    POSITIVE LOGITS
     You
    0.10
     Vimeo
    0.09
     disponível
    0.09
     ઉપલબ્ધ
    0.09
     erhältlich
    0.09
     વીડ
    0.09
     Spotify
    0.09
     lze
    0.09
     verfügbar
    0.09
     Etsy
    0.09
    Activations Density 0.005%

    No Known Activations