© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24714
    Prev
    Next
    INDEX
    Explanations

    bounding

    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
    afruit
    -0.08
     terrace
    -0.08
     sung
    -0.08
    idu
    -0.07
     sister
    -0.07
     fountain
    -0.07
     Reds
    -0.07
     study
    -0.07
    �
    -0.07
    使命
    -0.07
    POSITIVE LOGITS
     confidence
    0.10
     Confidence
    0.10
    confidence
    0.10
     naslov
    0.09
     Armani
    0.09
     econ
    0.09
    νο
    0.09
    Confidence
    0.09
    _inches
    0.08
    -confidence
    0.08
    Activations Density 0.004%

    No Known Activations