Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110014
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
     Reef
    -0.08
    HJ
    -0.08
     helmet
    -0.08
    ...↵↵↵↵
    -0.08
     Ike
    -0.08
     motive
    -0.08
     respekt
    -0.07
     Mink
    -0.07
     teddy
    -0.07
     уваж
    -0.07
    POSITIVE LOGITS
    *.
    0.07
     बन
    0.07
     Absatz
    0.07
    _corr
    0.07
    Perc
    0.07
     Xi
    0.07
     czyli
    0.07
     lett
    0.07
     Perc
    0.06
    硕
    0.06
    Activations Density 0.096%

    No Known Activations