© 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. 3-RESID-POST-AA
    11. 1496
    Prev
    Next
    INDEX
    Explanations

    Web page 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_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cube
    -0.09
    claims
    -0.08
    rolled
    -0.08
    normally
    -0.08
    stats
    -0.08
    .mongo
    -0.08
    evt
    -0.08
     panc
    -0.08
    lies
    -0.08
     ағ
    -0.08
    POSITIVE LOGITS
     apro
    0.09
    0.08
     Tucker
    0.08
     LEFT
    0.07
     LDL
    0.07
     *,↵
    0.07
     izquierda
    0.07
     संश
    0.07
     accordance
    0.07
     có
    0.07
    Activations Density 0.627%
    No Known Activations