© 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. 24776
    Prev
    Next
    INDEX
    Explanations

    Ruth

    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
    st
    -0.08
     ~/.
    -0.08
    所得
    -0.07
    配置
    -0.07
    AMA
    -0.07
     PDT
    -0.07
    ファ
    -0.07
     St
    -0.06
    لك
    -0.06
    NSError
    -0.06
    POSITIVE LOGITS
     poslov
    0.09
    phony
    0.08
     sworn
    0.08
     selvfølgelig
    0.08
     dermed
    0.08
     centuries
    0.08
    ffffff
    0.08
     solidar
    0.08
    \:
    0.08
     dryness
    0.08
    Activations Density 0.001%

    No Known Activations