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. 53872
    Prev
    Next
    INDEX
    Explanations

    efficient

    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
     details
    -0.09
     slope
    -0.08
     segment
    -0.08
     direction
    -0.07
     detalhes
    -0.07
     TSR
    -0.07
    Slope
    -0.07
     mater
    -0.07
     Teng
    -0.07
     slide
    -0.07
    POSITIVE LOGITS
    anyol
    0.08
    kins
    0.08
    _STACK
    0.08
    queued
    0.08
    istar
    0.08
    avoid
    0.08
    cheap
    0.08
    oworld
    0.08
    ownership
    0.07
     eater
    0.07
    Activations Density 0.000%

    No Known Activations