© 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. 31016
    Prev
    Next
    INDEX
    Explanations

    Marketing copy

    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
    адан
    -0.07
    УР
    -0.07
    оскольку
    -0.07
    ]++;↵
    -0.07
     terminating
    -0.07
     krijg
    -0.07
     politico
    -0.07
     cartel
    -0.07
    гәр
    -0.07
     terce
    -0.07
    POSITIVE LOGITS
     mention
    0.10
    mention
    0.10
     Mention
    0.10
     mentioning
    0.10
     blah
    0.10
     erwäh
    0.09
     XYZ
    0.09
     있다는
    0.08
    ，比如
    0.08
     وكيف
    0.08
    Activations Density 0.174%

    No Known Activations