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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 91142
    Prev
    Next
    INDEX
    Explanations

    grap

    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
    .cloud
    -0.08
    iker
    -0.08
     মূল
    -0.08
    wirk
    -0.08
    acad
    -0.07
     RV
    -0.07
    全民
    -0.07
     Wolfs
    -0.07
     Along
    -0.07
     LAS
    -0.07
    POSITIVE LOGITS
    Destructor
    0.09
     Move
    0.08
     مرب
    0.08
     сти
    0.08
     pengh
    0.07
     pux
    0.07
    Manipulator
    0.07
    Moves
    0.07
     Separator
    0.07
     reserved
    0.07
    Activations Density 0.002%

    No Known Activations