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. 11665
    Prev
    Next
    INDEX
    Explanations

    ice

    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
    ש
    -0.08
     Fuk
    -0.08
    hait
    -0.07
    vek
    -0.07
     pu
    -0.07
     renaissance
    -0.07
     зал
    -0.07
     elective
    -0.07
    Nov
    -0.07
    -0.07
    POSITIVE LOGITS
    breaker
    0.09
     spor
    0.09
    பெ
    0.09
     mist
    0.08
    bergs
    0.08
     rink
    0.08
     Cream
    0.08
     �
    0.08
     Ice
    0.08
     klart
    0.08
    Activations Density 0.010%

    No Known Activations