Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90411
    Prev
    Next
    INDEX
    Explanations

    Code, math, or quotes

    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
     PI
    -0.08
    -I
    -0.08
     prohibit
    -0.08
    -response
    -0.07
    GI
    -0.07
    -letter
    -0.07
    _SAMPLE
    -0.07
     iremos
    -0.07
     Palmer
    -0.07
     Psych
    -0.07
    POSITIVE LOGITS
    斗
    0.08
    ształ
    0.08
    如何
    0.08
    通过
    0.08
    断
    0.08
    为了
    0.08
     êtres
    0.07
     seres
    0.07
     ಹೇ
    0.07
     Dao
    0.07
    Activations Density 0.000%

    No Known Activations