© 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. 19-RESID-POST-AA
    11. 103045
    Prev
    Next
    INDEX
    Explanations

    blue

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    овали
    -0.09
    овало
    -0.09
    ised
    -0.08
    лэл
    -0.08
    IZATION
    -0.08
    ление
    -0.08
     khá
    -0.08
    izr
    -0.08
     ήδη
    -0.08
    ующий
    -0.08
    POSITIVE LOGITS
    berry
    0.13
    prints
    0.13
    berries
    0.12
    -green
    0.12
    -blue
    0.11
    -gray
    0.11
    -grey
    0.11
    vio
    0.11
    bells
    0.10
    birds
    0.10
    Activations Density 0.021%

    No Known Activations