© 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. 45259
    Prev
    Next
    INDEX
    Explanations

    math proofs

    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
     лиш
    -0.08
     upbeat
    -0.08
    不限
    -0.08
     Summer
    -0.08
     consac
    -0.08
    boxed
    -0.08
     veľ
    -0.08
    brief
    -0.08
     brightly
    -0.08
     છતાં
    -0.08
    POSITIVE LOGITS
     illusions
    0.09
     invari
    0.08
     forth
    0.08
    asas
    0.07
     calculations
    0.07
     peculiar
    0.07
     symmetry
    0.07
     somehow
    0.07
    mess
    0.07
    0.07
    Activations Density 0.096%
    No Known Activations