Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53428
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    weka
    -0.08
     aand
    -0.07
    �
    -0.07
    .errors
    -0.07
    ేద
    -0.07
     edging
    -0.07
     deta
    -0.07
    �
    -0.07
    -head
    -0.07
     보
    -0.07
    POSITIVE LOGITS
     Ogun
    0.08
    .Handler
    0.08
    IBAction
    0.08
     Unexpected
    0.08
     physi
    0.08
     triggered
    0.08
    handler
    0.08
    Handler
    0.08
     ಸಂಭವ
    0.08
     نفسي
    0.08
    Activations Density 0.014%

    No Known Activations