© 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. 110699
    Prev
    Next
    INDEX
    Explanations

    math expressions and functions

    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
    .hikari
    -0.08
    .Hikari
    -0.08
    (',
    -0.08
    .controls
    -0.08
    Diet
    -0.08
     הממשלה
    -0.08
     competitors
    -0.08
     sensational
    -0.07
    Dipl
    -0.07
     minimizing
    -0.07
    POSITIVE LOGITS
     Covered
    0.09
    чи
    0.09
     modulo
    0.08
     covered
    0.08
     Audio
    0.08
     erased
    0.08
     tranquille
    0.08
     octave
    0.08
     Psycho
    0.08
     cyc
    0.08
    Activations Density 0.038%

    No Known Activations