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. 44711
    Prev
    Next
    INDEX
    Explanations

    or add

    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
    @Api
    -0.08
     altında
    -0.08
    吧
    -0.08
     proph
    -0.08
    vt
    -0.07
    Api
    -0.07
    fl
    -0.07
    frag
    -0.07
    ỏa
    -0.07
     considerations
    -0.07
    POSITIVE LOGITS
     Duration
    0.10
     duration
    0.09
    -duration
    0.09
     duración
    0.08
    Duration
    0.08
    .Duration
    0.08
     количества
    0.08
     Slight
    0.08
     endurance
    0.08
    .duration
    0.08
    Activations Density 0.004%

    No Known Activations