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. 117444
    Prev
    Next
    INDEX
    Explanations

    yo

    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
     تصميم
    -0.08
    ovima
    -0.08
    cess
    -0.08
    configured
    -0.08
    etheus
    -0.08
    proposal
    -0.07
    át
    -0.07
     découvre
    -0.07
    cession
    -0.07
    ceptor
    -0.07
    POSITIVE LOGITS
     уж
    0.09
     vapor
    0.08
    _na
    0.08
     mainland
    0.08
     booming
    0.07
    	va
    0.07
     ouder
    0.07
     iink
    0.07
    _TREE
    0.07
     ánimo
    0.07
    Activations Density 0.000%

    No Known Activations