© 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. 23-RESID-POST-AA
    11. 51828
    Prev
    Next
    INDEX
    Explanations

    say "3"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zh
    -0.09
    гра
    -0.09
     employment
    -0.08
     GP
    -0.08
    .styleable
    -0.08
    municip
    -0.08
    .toolbar
    -0.08
     shoppen
    -0.08
     roadway
    -0.08
    >K
    -0.08
    POSITIVE LOGITS
     ಲೋಕ
    0.08
    DLL
    0.07
     DLL
    0.07
     резерв
    0.07
     ELF
    0.07
     regler
    0.07
    _itr
    0.07
    (cf
    0.07
    _SO
    0.07
     wann
    0.07
    Activations Density 0.008%

    No Known Activations