© 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. 11-RESID-POST-AA
    11. 70880
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shannon
    -0.08
    Und
    -0.07
     ramp
    -0.07
    ality
    -0.07
    hel
    -0.07
    .orm
    -0.07
    urry
    -0.07
     Und
    -0.07
    otyp
    -0.06
    WORDS
    -0.06
    POSITIVE LOGITS
     simpl
    0.11
     simplifying
    0.10
    simpl
    0.10
     simplifies
    0.09
     Expr
    0.09
     expresa
    0.09
     simplify
    0.09
     tedious
    0.09
     പൊ
    0.09
     diferencial
    0.08
    Activations Density 0.054%

    No Known Activations