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. 12742
    Prev
    Next
    INDEX
    Explanations

    @

    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
     findet
    -0.07
    thair
    -0.07
     tento
    -0.07
    ગર
    -0.07
     식
    -0.07
     breasts
    -0.07
     pá
    -0.07
    ціон
    -0.07
    air
    -0.07
     که
    -0.07
    POSITIVE LOGITS
     distress
    0.08
     treg
    0.07
     +=
    0.07
    _dic
    0.07
    dic
    0.07
     itt
    0.07
    dept
    0.07
    eldig
    0.07
     étern
    0.07
     viscos
    0.07
    Activations Density 0.006%

    No Known Activations