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. 53858
    Prev
    Next
    INDEX
    Explanations

    logical deduction, knowing

    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
     malah
    -0.08
     mille
    -0.08
    	include
    -0.08
     tariffs
    -0.07
    funk
    -0.07
     выдерж
    -0.07
    śred
    -0.07
     nostalgia
    -0.07
    urcharge
    -0.07
    名称
    -0.07
    POSITIVE LOGITS
     inferred
    0.13
     inference
    0.12
     certainty
    0.11
     conclus
    0.10
     infer
    0.10
    Inference
    0.10
     Cert
    0.09
    ferences
    0.09
     definitive
    0.09
     Safe
    0.09
    Activations Density 0.011%

    No Known Activations