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. 431
    Prev
    Next
    INDEX
    Explanations

    isn't

    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
     takeaway
    -0.08
     Jamaican
    -0.07
    _prime
    -0.07
     prog
    -0.07
     coc
    -0.07
    (cp
    -0.07
    lios
    -0.07
    perc
    -0.07
    <|endoftext|>
    -0.07
     Pry
    -0.07
    POSITIVE LOGITS
    ิโน
    0.08
     missen
    0.08
     unfamiliar
    0.08
     irreversible
    0.08
     pesado
    0.08
     قط
    0.08
     ignorance
    0.07
     //--------------------------------
    0.07
    Ignored
    0.07
     смерть
    0.07
    Activations Density 0.000%

    No Known Activations