© 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. 70969
    Prev
    Next
    INDEX
    Explanations

    fixed

    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
    Ther
    -0.08
    warden
    -0.08
     вдох
    -0.07
     desesper
    -0.07
    diff
    -0.07
    nir
    -0.07
     Chill
    -0.07
     Therm
    -0.07
    Jam
    -0.07
    insp
    -0.07
    POSITIVE LOGITS
     fixed
    0.14
    固定
    0.14
     מראש
    0.13
     predetermined
    0.13
    _fixed
    0.12
    -fixed
    0.12
     Fixed
    0.12
     fijo
    0.11
    .fixed
    0.11
    .Fixed
    0.11
    Activations Density 0.026%

    No Known Activations