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. 75247
    Prev
    Next
    INDEX
    Explanations

    have

    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
     Maschinen
    -0.07
    _MACHINE
    -0.07
     물론
    -0.07
    _machine
    -0.07
     USPS
    -0.07
     slee
    -0.07
     postoje
    -0.07
     Machine
    -0.07
     tirs
    -0.07
    Machine
    -0.07
    POSITIVE LOGITS
     sard
    0.08
     pão
    0.08
    GUID
    0.08
    emonic
    0.08
    еда
    0.08
    धा
    0.07
    Connect
    0.07
    .rel
    0.07
    ètement
    0.07
    ampf
    0.07
    Activations Density 0.003%

    No Known Activations