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. 53211
    Prev
    Next
    INDEX
    Explanations

    bad

    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
     shadows
    -0.08
     പിന്ന
    -0.08
     والح
    -0.08
    .sh
    -0.08
     hazards
    -0.07
     தெ
    -0.07
     imaginative
    -0.07
    وظ
    -0.07
     سير
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    指定
    0.10
     negotiating
    0.09
     specified
    0.09
    nes
    0.08
    queeze
    0.08
     spéc
    0.08
    əni
    0.08
     negotiate
    0.08
     overeenkomst
    0.08
     tolerated
    0.07
    Activations Density 0.004%

    No Known Activations