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. 76331
    Prev
    Next
    INDEX
    Explanations

    numeric input in code

    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
    "(
    -0.07
     vast
    -0.07
    Mill
    -0.07
    "D
    -0.07
     tensions
    -0.07
     expansions
    -0.07
    ize
    -0.07
    就是
    -0.07
    DAV
    -0.07
     Poc
    -0.07
    POSITIVE LOGITS
     remed
    0.09
     reconsider
    0.09
     Charakter
    0.09
     permane
    0.09
     �
    0.08
    čne
    0.08
     invalidate
    0.08
     underm
    0.08
    ivt
    0.07
     recom
    0.07
    Activations Density 0.005%

    No Known Activations