© 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. 3-RESID-POST-AA
    11. 12956
    Prev
    Next
    INDEX
    Explanations

    polymerase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    965
    -0.08
    ország
    -0.08
     vlo
    -0.07
    icznych
    -0.07
    _ATTRIBUTES
    -0.07
    ktf
    -0.07
    966
    -0.07
    landais
    -0.07
    ическими
    -0.07
    942
    -0.07
    POSITIVE LOGITS
     구
    0.09
    .Dot
    0.08
     Honda
    0.08
     pigment
    0.08
    정
    0.07
    Honda
    0.07
     HMS
    0.07
     Tune
    0.07
    -hole
    0.07
     HIV
    0.07
    Activations Density 0.002%

    No Known Activations