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. 9114
    Prev
    Next
    INDEX
    Explanations

    determined

    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
    哪里
    -0.08
     swollen
    -0.08
     hz
    -0.08
    749
    -0.07
    _nan
    -0.07
     overwhelmed
    -0.07
    ways
    -0.07
     revised
    -0.07
     breakout
    -0.07
    利用
    -0.07
    POSITIVE LOGITS
    written
    0.08
     whim
    0.07
    .rules
    0.07
    Charl
    0.07
     Schr
    0.07
     Hait
    0.07
    ulu
    0.07
    ಾದ
    0.07
    �
    0.07
    sequ
    0.07
    Activations Density 0.008%

    No Known Activations