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. 103069
    Prev
    Next
    INDEX
    Explanations

    struction

    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
     Merc
    -0.08
    Merc
    -0.08
    Mét
    -0.07
    .Status
    -0.07
     सहज
    -0.07
     μια
    -0.07
     దర్శ
    -0.07
     стоимость
    -0.07
     οικο
    -0.07
     τις
    -0.07
    POSITIVE LOGITS
    /questions
    0.09
     asking
    0.09
     komment
    0.08
     Wh
    0.08
     gjelder
    0.08
     પૂછ
    0.08
    ဘာ
    0.08
     teks
    0.08
     opmerkingen
    0.08
    文本
    0.08
    Activations Density 0.001%

    No Known Activations