© 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. 11-RESID-POST-AA
    11. 24631
    Prev
    Next
    INDEX
    Explanations

    resident

    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
     Reverse
    -0.08
     swallow
    -0.08
     reverse
    -0.07
     ly
    -0.07
    rot
    -0.07
     ninu
    -0.07
    дох
    -0.07
     జరిగింది
    -0.07
    posite
    -0.07
     reversed
    -0.07
    POSITIVE LOGITS
    :innen
    0.10
    居民
    0.09
    habit
    0.08
     الذين
    0.08
    Jessica
    0.08
     bere
    0.08
     contribu
    0.08
    /operators
    0.08
     sekitar
    0.08
    *innen
    0.08
    Activations Density 0.021%

    No Known Activations