© 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. 11-RESID-POST-AA
    11. 129503
    Prev
    Next
    INDEX
    Explanations

    total

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dlg
    -0.08
    仕様
    -0.08
    ijn
    -0.08
    ittaa
    -0.08
     જગ
    -0.08
    Txn
    -0.08
    _dt
    -0.08
     spre
    -0.07
    chosen
    -0.07
     പോലെ
    -0.07
    POSITIVE LOGITS
     есеп
    0.08
     お
    0.08
     Tutt
    0.07
     Coastal
    0.07
     totaled
    0.07
     had
    0.07
     Southeastern
    0.07
     threatened
    0.07
    、お
    0.07
    אָס
    0.07
    Activations Density 0.033%

    No Known Activations