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. 76403
    Prev
    Next
    INDEX
    Explanations

    :

    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
    (record
    -0.08
     Stre
    -0.08
     spe
    -0.07
    uffle
    -0.07
    -use
    -0.07
    aketa
    -0.07
    avit
    -0.07
     use
    -0.07
     finely
    -0.07
    ARB
    -0.07
    POSITIVE LOGITS
     আবার
    0.10
     Again
    0.09
     снова
    0.09
    Again
    0.09
     nochmals
    0.09
     വീണ്ടും
    0.09
     again
    0.09
     يرى
    0.08
     ফিরে
    0.08
     שוב
    0.08
    Activations Density 0.034%

    No Known Activations