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. 52844
    Prev
    Next
    INDEX
    Explanations

    intersection

    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
     acknowledged
    -0.09
     acknowled
    -0.08
     aggregated
    -0.08
     acknowledging
    -0.08
     acknowledges
    -0.08
     citing
    -0.08
     zeggen
    -0.08
    .zaxxer
    -0.08
     Correction
    -0.07
     variados
    -0.07
    POSITIVE LOGITS
     viable
    0.10
     intersection
    0.08
    intersection
    0.08
    indlela
    0.08
    解
    0.08
    arity
    0.08
     nzira
    0.07
     માર્ગ
    0.07
     feasibility
    0.07
     driveway
    0.07
    Activations Density 0.014%

    No Known Activations