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. 112830
    Prev
    Next
    INDEX
    Explanations

    asked

    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
     spise
    -0.08
     hauptsächlich
    -0.08
    ஞ
    -0.08
     söö
    -0.08
     ainakin
    -0.07
    umbuhan
    -0.07
    ання
    -0.07
     mornings
    -0.07
     događ
    -0.07
     drummer
    -0.07
    POSITIVE LOGITS
     ನೆರ
    0.07
     मदद
    0.07
    fordert
    0.07
     सहायता
    0.07
     സഹായ
    0.07
    fordern
    0.07
     ?>/
    0.07
     mel
    0.07
     Nant
    0.07
    XE
    0.07
    Activations Density 0.004%

    No Known Activations