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. 12242
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ahr
    -0.09
    arger
    -0.08
    争
    -0.08
     liebe
    -0.08
     رضي
    -0.08
     attends
    -0.07
    ahrung
    -0.07
    走
    -0.07
    fty
    -0.07
     Whether
    -0.07
    POSITIVE LOGITS
    .sim
    0.08
    0.08
    -legged
    0.08
    Annotations
    0.08
     simul
    0.07
    _constraints
    0.07
    Constraints
    0.07
     simulations
    0.07
    SIM
    0.07
     оз
    0.07
    Activations Density 0.062%

    No Known Activations