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. 90298
    Prev
    Next
    INDEX
    Explanations

    0

    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
    -thread
    -0.09
    集团
    -0.08
    (group
    -0.07
     hoogwaardige
    -0.07
     proche
    -0.07
     confisc
    -0.07
     strán
    -0.07
     hugged
    -0.07
    允
    -0.07
     sweets
    -0.07
    POSITIVE LOGITS
     egw
    0.08
     определ
    0.08
     ар
    0.07
    
    0.07
    олж
    0.07
    .state
    0.07
     explot
    0.07
    erit
    0.07
     maak
    0.07
    альным
    0.07
    Activations Density 0.000%

    No Known Activations