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. 67353
    Prev
    Next
    INDEX
    Explanations

    eless

    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
     spelling
    -0.08
     נע
    -0.08
     пен
    -0.08
    .sd
    -0.08
     આવ
    -0.07
     قدرت
    -0.07
     Equation
    -0.07
     Hockey
    -0.07
     Aad
    -0.07
    ાણી
    -0.07
    POSITIVE LOGITS
    __((
    0.08
    арын
    0.08
    _PLACE
    0.08
    fully
    0.07
     foodie
    0.07
    лайн
    0.07
    Place
    0.07
     weighs
    0.07
    Ticks
    0.07
     savet
    0.07
    Activations Density 0.004%

    No Known Activations