© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 47966
    Prev
    Next
    INDEX
    Explanations

    meng

    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
     Valentine's
    -0.08
    -Oct
    -0.08
    elfeld
    -0.08
    woordig
    -0.08
    gunakan
    -0.07
     Christmas
    -0.07
    hão
    -0.07
    JOR
    -0.07
     નંબર
    -0.07
    -0.07
    POSITIVE LOGITS
    angkat
    0.11
    anggap
    0.10
    arus
    0.09
    untary
    0.09
    arah
    0.08
    uat
    0.08
    unt
    0.08
    asim
    0.08
     us
    0.08
    us
    0.08
    Activations Density 0.000%
    No Known Activations