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. 101514
    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
     ஒர
    -0.08
     congen
    -0.07
    ?k
    -0.07
    yr
    -0.07
    's
    -0.07
     protagonista
    -0.07
    ک
    -0.07
     வே
    -0.07
     ஒ
    -0.07
    %C
    -0.07
    POSITIVE LOGITS
     eleição
    0.09
     geholpen
    0.08
     élections
    0.08
     nephews
    0.08
    _cols
    0.08
    utuhan
    0.08
     polí
    0.08
     Eugene
    0.08
     투
    0.08
     Engineering
    0.07
    Activations Density 0.000%

    No Known Activations