© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 19088
    Prev
    Next
    INDEX
    Explanations

    code assignment/return

    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
    =len
    -0.10
     /\.
    -0.08
    .done
    -0.08
     قار
    -0.08
    ritic
    -0.07
    ="../
    -0.07
     involved
    -0.07
    -threat
    -0.07
     researcher
    -0.07
     কাছে
    -0.07
    POSITIVE LOGITS
     Types
    0.09
     Neither
    0.09
     Only
    0.08
    	Type
    0.08
     types
    0.08
     Sticky
    0.08
    -types
    0.08
     functionalities
    0.08
    გვ
    0.08
     Guys
    0.08
    Activations Density 0.001%

    No Known Activations