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. 90284
    Prev
    Next
    INDEX
    Explanations

    it

    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
    _volume
    -0.09
     обязательно
    -0.08
    .volume
    -0.08
    -volume
    -0.08
    Volume
    -0.08
    (volume
    -0.08
     volumen
    -0.08
    volume
    -0.08
     volumes
    -0.08
    /icons
    -0.08
    POSITIVE LOGITS
     simmer
    0.09
    ાટી
    0.07
     Answer
    0.07
    ಾಗ
    0.07
    躁
    0.07
    ટ
    0.07
    ક્ષ
    0.07
    reshold
    0.07
     checks
    0.07
     depuis
    0.07
    Activations Density 0.010%

    No Known Activations