© 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. 2551
    Prev
    Next
    INDEX
    Explanations

    .com

    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
     TBD
    -0.08
     killings
    -0.08
     dia
    -0.07
     encouragement
    -0.07
     nhi
    -0.07
     संप
    -0.07
     don
    -0.07
     vh
    -0.07
     yek
    -0.07
     रिश
    -0.07
    POSITIVE LOGITS
     Goodman
    0.09
     Loader
    0.09
     stretches
    0.08
    Wal
    0.08
    Loader
    0.08
    privacy
    0.07
     Palmas
    0.07
    _LOADING
    0.07
    truth
    0.07
     ANI
    0.07
    Activations Density 0.000%

    No Known Activations