© 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. 102791
    Prev
    Next
    INDEX
    Explanations

    time

    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
     demanding
    -0.09
     as
    -0.07
     imposing
    -0.07
     daunting
    -0.07
     infe
    -0.07
    29
    -0.07
    造成
    -0.07
     autonomy
    -0.07
     flat
    -0.07
    ึ้น
    -0.07
    POSITIVE LOGITS
     была
    0.12
     was
    0.12
    was
    0.11
    Was
    0.11
     был
    0.11
     była
    0.10
     Was
    0.10
     wasnt
    0.10
     wasa
    0.10
     sanitizer
    0.09
    Activations Density 0.001%

    No Known Activations