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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1564
    Prev
    Next
    INDEX
    Explanations

    dimensional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ころ
    -0.08
    くら
    -0.08
    MIS
    -0.08
     �
    -0.08
     DEG
    -0.08
     Cedar
    -0.08
    頃
    -0.08
     suspended
    -0.07
    -DE
    -0.07
     внес
    -0.07
    POSITIVE LOGITS
     mo
    0.08
     zend
    0.08
     affair
    0.08
     Moll
    0.07
     affiliate
    0.07
     symmetrical
    0.07
     vomiting
    0.07
    ענ
    0.07
    วน
    0.07
    gar
    0.07
    Activations Density 0.002%

    No Known Activations