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. 117653
    Prev
    Next
    INDEX
    Explanations

    shallow

    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
    Foods
    -0.08
     provision
    -0.08
     monument
    -0.08
    که
    -0.08
    _watch
    -0.08
    larni
    -0.08
    jata
    -0.08
    ltal
    -0.08
    belasting
    -0.07
     برا
    -0.07
    POSITIVE LOGITS
     maxlength
    0.08
     Hex
    0.08
    距
    0.07
     hg
    0.07
     камера
    0.07
     rs
    0.07
     साह
    0.07
    RSS
    0.07
     yihiin
    0.07
    摄影
    0.07
    Activations Density 0.001%

    No Known Activations