© 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. 51513
    Prev
    Next
    INDEX
    Explanations

    At

    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
     шару
    -0.07
    rides
    -0.07
     там
    -0.07
    ',['../
    -0.07
    /"+
    -0.07
     clips
    -0.07
     "+
    -0.07
     concent
    -0.06
    Precision
    -0.06
    ×↵↵
    -0.06
    POSITIVE LOGITS
    enderror
    0.09
    essar
    0.08
     tila
    0.08
     jabón
    0.08
     lwj
    0.08
     shqipt
    0.08
     wad
    0.08
     Kuwait
    0.08
    fors
    0.08
    curl
    0.08
    Activations Density 0.000%

    No Known Activations