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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 95091
    Prev
    Next
    INDEX
    Explanations

    .

    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
    क्त
    -0.08
    ट
    -0.08
    염
    -0.08
     terrorist
    -0.08
    ड
    -0.08
     tweak
    -0.07
     गुर
    -0.07
    न्�
    -0.07
    }&
    -0.07
    秦
    -0.07
    POSITIVE LOGITS
    เหตุ
    0.08
     внес
    0.08
    /inter
    0.08
     જ
    0.08
     Orchard
    0.07
     Alten
    0.07
     ભૂ
    0.07
    Disposition
    0.07
     intervent
    0.07
    häuser
    0.07
    Activations Density 0.015%

    No Known Activations