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. 101751
    Prev
    Next
    INDEX
    Explanations

    third

    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
    pares
    -0.07
    apos
    -0.07
    _PENDING
    -0.07
     Employers
    -0.07
     candid
    -0.07
    ür
    -0.07
    ทำ
    -0.07
    ilt
    -0.07
    pending
    -0.07
    [element
    -0.07
    POSITIVE LOGITS
     ко
    0.09
     бошад
    0.09
     хайр
    0.09
    ახებ
    0.08
     аха
    0.08
    აუბ
    0.08
     recount
    0.08
     préférence
    0.08
     ficar
    0.08
     იქნ
    0.08
    Activations Density 0.006%

    No Known Activations