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. 111635
    Prev
    Next
    INDEX
    Explanations

    PCB components

    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
     crust
    -0.07
    /kernel
    -0.07
    (kernel
    -0.07
     kernel
    -0.07
     wynik
    -0.07
    Calculator
    -0.07
    TZ
    -0.07
    herlands
    -0.07
    مران
    -0.07
    ',"
    -0.06
    POSITIVE LOGITS
     Form
    0.09
    isible
    0.08
    _form
    0.08
    _FORM
    0.08
    _languages
    0.08
    Form
    0.08
     Nec
    0.08
     tagline
    0.08
    _STYLE
    0.08
    .form
    0.08
    Activations Density 0.003%

    No Known Activations