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. 15-RESID-POST-AA
    6. 18842
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bounded
    -0.09
     not
    -0.08
    not
    -0.08
    B
    -0.08
    _converter
    -0.08
     such
    -0.08
    .strip
    -0.08
     common
    -0.08
     less
    -0.08
     converter
    -0.08
    POSITIVE LOGITS
    éanmoins
    0.09
     Però
    0.09
    ärkung
    0.09
     __("
    0.09
     !***
    0.08
    würdigkeiten
    0.08
     Institutions
    0.08
     Nowadays
    0.08
     addu
    0.08
    hebbers
    0.08
    Activations Density 0.003%

    No Known Activations