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. 9210
    Prev
    Next
    INDEX
    Explanations

    problem

    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
    Sticky
    -0.10
    rag
    -0.08
     pocket
    -0.07
    sticky
    -0.07
    Retry
    -0.07
    μέ
    -0.07
     sticky
    -0.07
     Sticky
    -0.07
     renovating
    -0.07
    وب
    -0.07
    POSITIVE LOGITS
     предот
    0.08
     iarr
    0.08
     initiated
    0.08
    bodaeth
    0.08
     Judges
    0.08
     күрһәт
    0.08
     зь
    0.08
    wirtschaft
    0.08
     XVII
    0.08
     eby
    0.08
    Activations Density 0.001%

    No Known Activations