© 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. 102626
    Prev
    Next
    INDEX
    Explanations

    means

    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
     считает
    -0.07
    Seems
    -0.07
     olduğ
    -0.07
    Een
    -0.07
    賞
    -0.07
    Due
    -0.07
    Bh
    -0.07
    پس
    -0.07
    Ĉ
    -0.07
    Where
    -0.07
    POSITIVE LOGITS
    fully
    0.12
     anything
    0.11
     different
    0.11
     by
    0.11
     diferente
    0.10
    -by
    0.10
     nothing
    0.10
    ery
    0.10
     there's
    0.10
     משהו
    0.10
    Activations Density 0.039%

    No Known Activations