© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68300
    Prev
    Next
    INDEX
    Explanations

    Common and non-specific words

    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
     conversion
    -0.08
    �
    -0.08
    設
    -0.08
    須
    -0.08
     conç
    -0.07
    conversion
    -0.07
     可
    -0.07
     distinction
    -0.07
     हे
    -0.07
    converter
    -0.07
    POSITIVE LOGITS
    ίνη
    0.09
     NUE
    0.08
    binations
    0.07
    aalada
    0.07
    ිබ
    0.07
     Bewohner
    0.07
     groene
    0.07
    _people
    0.07
     morar
    0.07
    ohan
    0.07
    Activations Density 0.000%

    No Known Activations