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. 48958
    Prev
    Next
    INDEX
    Explanations

    boolean

    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
     Pueblo
    -0.09
    徐
    -0.09
     mand
    -0.08
     wholly
    -0.08
    anyak
    -0.07
     गरीब
    -0.07
     kwe
    -0.07
     Lei
    -0.07
    ्ण
    -0.07
     Synd
    -0.07
    POSITIVE LOGITS
    -valu
    0.10
    ISH
    0.08
     prob
    0.08
    _repr
    0.07
    _like
    0.07
     fo
    0.07
    oader
    0.07
    IAN
    0.07
     isset
    0.07
    .micro
    0.07
    Activations Density 0.003%

    No Known Activations