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. 30321
    Prev
    Next
    INDEX
    Explanations

    intervals and being between

    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
    cony
    -0.08
     Bing
    -0.08
     verkeer
    -0.07
    indexes
    -0.07
     Vrij
    -0.07
    vind
    -0.07
    -total
    -0.07
     lup
    -0.07
     enables
    -0.07
     değerl
    -0.07
    POSITIVE LOGITS
    .prev
    0.09
     самостоятельно
    0.09
     vone
    0.08
    .Next
    0.08
     ближай
    0.08
    隔
    0.08
    ователь
    0.08
     промеж
    0.07
    uation
    0.07
     વચ્ચે
    0.07
    Activations Density 0.017%

    No Known Activations