© 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. 2684
    Prev
    Next
    INDEX
    Explanations

    back

    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
     Carrie
    -0.09
     Citizens
    -0.08
     læ
    -0.08
     citizens
    -0.08
     civ
    -0.08
     muscles
    -0.07
    Loved
    -0.07
     LTE
    -0.07
     victim
    -0.07
    KE
    -0.07
    POSITIVE LOGITS
    ิ
    0.08
     quyền
    0.08
    орож
    0.08
    یک
    0.08
     violent
    0.07
     Pren
    0.07
    (Screen
    0.07
     wides
    0.07
    instancetype
    0.07
    권
    0.07
    Activations Density 0.000%

    No Known Activations