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. 112777
    Prev
    Next
    INDEX
    Explanations

    colon

    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
    cape
    -0.08
    arrera
    -0.08
     @_;↵
    -0.08
    zul
    -0.08
    Cape
    -0.08
    Sant
    -0.08
    出来
    -0.07
    remaining
    -0.07
    Zo
    -0.07
    Remaining
    -0.07
    POSITIVE LOGITS
     Excellent
    0.09
    Indeed
    0.09
     Indeed
    0.09
     fascinating
    0.08
     తాజ
    0.08
     impressive
    0.08
    最新
    0.08
    Excellent
    0.08
     excellent
    0.08
     adopting
    0.08
    Activations Density 0.014%

    No Known Activations