© 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. 95013
    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
     dado
    -0.08
    ခံ
    -0.08
    镜
    -0.08
     paradox
    -0.07
     पत
    -0.07
    $/,
    -0.07
     Arc
    -0.07
     laminate
    -0.07
     Gordon
    -0.07
    λά
    -0.07
    POSITIVE LOGITS
    Eight
    0.09
    .sort
    0.09
    avil
    0.08
    .List
    0.08
    _are
    0.08
     poss
    0.08
    Distances
    0.08
    igns
    0.08
     които
    0.08
    MES
    0.08
    Activations Density 0.075%

    No Known Activations