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. 42086
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    _FREE
    -0.08
     lately
    -0.08
    ”、“
    -0.07
    /address
    -0.07
    _plane
    -0.07
     Können
    -0.07
    _CM
    -0.07
    .Grid
    -0.07
    _grid
    -0.07
     Kann
    -0.07
    POSITIVE LOGITS
     sede
    0.09
     gabe
    0.09
     tenant
    0.08
     Ignacio
    0.08
     Tenant
    0.08
     ono
    0.08
     автоном
    0.08
    etho
    0.08
     cliënt
    0.07
     pepe
    0.07
    Activations Density 0.148%

    No Known Activations