© 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. 23-RESID-POST-AA
    11. 97317
    Prev
    Next
    INDEX
    Explanations

    unusual

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sufficient
    -0.07
     suficientes
    -0.07
    _full
    -0.07
    plete
    -0.07
     Definit
    -0.07
    herent
    -0.07
    provements
    -0.07
    ufficient
    -0.07
    _basic
    -0.07
     yeter
    -0.06
    POSITIVE LOGITS
     unusual
    0.57
     weird
    0.53
     ungewöhn
    0.51
     bizarre
    0.49
     strange
    0.49
     необы
    0.48
     unconventional
    0.47
     étrange
    0.45
     peculiar
    0.43
     quirky
    0.42
    Activations Density 0.412%

    No Known Activations