© 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. 95173
    Prev
    Next
    INDEX
    Explanations

    the

    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
     tailored
    -0.08
    ®
    -0.07
     उन्ह
    -0.07
    (tm
    -0.07
     hamp
    -0.07
    ，却
    -0.07
     Polaris
    -0.07
    ין
    -0.07
    Pol
    -0.07
     keen
    -0.07
    POSITIVE LOGITS
     divisible
    0.10
     �
    0.08
     Assume
    0.08
    -div
    0.07
     laps
    0.07
     сос
    0.07
     (?
    0.07
     maximise
    0.07
     имеется
    0.07
     pendent
    0.07
    Activations Density 0.036%

    No Known Activations