Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 42034
    Prev
    Next
    INDEX
    Explanations

    Storytelling

    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
     reservoirs
    -0.08
     reservoir
    -0.08
     ixesha
    -0.08
    տեղ
    -0.08
     ფარგ
    -0.08
     געד
    -0.08
    icação
    -0.08
    ભળ
    -0.08
    ობლ
    -0.08
    Zimmer
    -0.08
    POSITIVE LOGITS
    order
    0.07
    0.07
     Enable
    0.07
    _enable
    0.07
    _spell
    0.07
    /test
    0.07
    _once
    0.07
     order
    0.07
    prot
    0.07
    irectory
    0.07
    Activations Density 0.000%

    No Known Activations