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. 49603
    Prev
    Next
    INDEX
    Explanations

    40

    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
     vorgenommen
    -0.10
    ethe
    -0.09
     във
    -0.09
     country's
    -0.08
    lite
    -0.08
     pretrained
    -0.08
     Inflation
    -0.08
     inflation
    -0.08
     sqrt
    -0.08
     hord
    -0.08
    POSITIVE LOGITS
    Gar
    0.07
     bleaching
    0.07
     approaching
    0.07
    _REPEAT
    0.07
    zy
    0.07
    /messages
    0.07
     ornament
    0.07
    番
    0.07
     tattoo
    0.07
    _rep
    0.07
    Activations Density 0.005%

    No Known Activations