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. 52859
    Prev
    Next
    INDEX
    Explanations

    find

    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
    orsa
    -0.09
     tribute
    -0.09
     hommage
    -0.09
     affiche
    -0.08
    Reblog
    -0.08
    -0.08
    Recycler
    -0.08
    -theme
    -0.08
     Ritual
    -0.08
     revenge
    -0.08
    POSITIVE LOGITS
     criteria
    0.10
     borderline
    0.10
     criterion
    0.10
    .criteria
    0.10
     discrimin
    0.10
     validity
    0.09
    valid
    0.09
     thresholds
    0.09
     parameter
    0.09
    criteria
    0.09
    Activations Density 0.119%

    No Known Activations