© 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. 30066
    Prev
    Next
    INDEX
    Explanations

    mixed languages/symbols

    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
     devotees
    -0.09
     हिम
    -0.08
     Buddha
    -0.08
     ভারতের
    -0.08
     procession
    -0.08
     Favor
    -0.08
     Herzog
    -0.07
     Incl
    -0.07
     sift
    -0.07
     mythology
    -0.07
    POSITIVE LOGITS
     editable
    0.13
    Editable
    0.12
     Editable
    0.12
    editable
    0.12
    _edit
    0.11
    _EDIT
    0.11
    .edit
    0.11
    editing
    0.11
    Editing
    0.11
     editing
    0.11
    Activations Density 0.005%

    No Known Activations