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. 46020
    Prev
    Next
    INDEX
    Explanations

    from

    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
     Kib
    -0.09
     Hemisphere
    -0.08
     통한
    -0.08
     जाइ
    -0.08
    illian
    -0.08
     Điều
    -0.08
    ักษ
    -0.08
     Validators
    -0.08
     evitare
    -0.08
     Lé
    -0.07
    POSITIVE LOGITS
     recognizable
    0.10
     imagine
    0.08
     trope
    0.08
     فیلم
    0.08
     ripe
    0.08
     joke
    0.07
    falls
    0.07
     take
    0.07
    battle
    0.07
     reconoc
    0.07
    Activations Density 0.004%

    No Known Activations