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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120268
    Prev
    Next
    INDEX
    Explanations

    1

    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
    ಿದೆ
    -0.08
     회사
    -0.08
     사이트
    -0.08
    ುದ
    -0.08
    ન્સ
    -0.08
    ંભ
    -0.07
    ения
    -0.07
    haften
    -0.07
     Dream
    -0.07
     facilité
    -0.07
    POSITIVE LOGITS
    infl
    0.08
    CO
    0.08
    rot
    0.08
    Clar
    0.08
     rik
    0.08
     tog
    0.08
     ting
    0.08
     Ting
    0.08
    Rot
    0.07
     Hein
    0.07
    Activations Density 0.017%

    No Known Activations