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. 46275
    Prev
    Next
    INDEX
    Explanations

    x

    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
    乳
    -0.09
    Enumeration
    -0.09
     Funnel
    -0.08
    ರ್ಥ
    -0.08
     enumeration
    -0.08
     lit
    -0.08
    自己
    -0.07
    Er
    -0.07
     lee
    -0.07
    legacy
    -0.07
    POSITIVE LOGITS
     clarity
    0.08
     Glad
    0.08
     coeff
    0.08
    انات
    0.07
    -solving
    0.07
     hvordan
    0.07
     favore
    0.07
     contrasted
    0.07
     investigation
    0.07
     سی
    0.07
    Activations Density 0.046%

    No Known Activations