© 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. 12810
    Prev
    Next
    INDEX
    Explanations

    sharply

    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
     cab
    -0.08
     rod
    -0.08
     lay
    -0.07
     miał
    -0.07
     ba
    -0.07
    \,
    -0.07
     unl
    -0.07
    orras
    -0.07
     �
    -0.07
     candid
    -0.07
    POSITIVE LOGITS
     jane
    0.08
     осво
    0.08
     fortunate
    0.08
     embraced
    0.08
     ionic
    0.08
     embracing
    0.08
     сочет
    0.08
     нар
    0.08
    ത്തോടെ
    0.07
    civil
    0.07
    Activations Density 0.003%

    No Known Activations