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. 45772
    Prev
    Next
    INDEX
    Explanations

    of

    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
    _du
    -0.08
    Signature
    -0.07
    orga
    -0.07
     dereg
    -0.07
     dém
    -0.07
    Descending
    -0.07
     signature
    -0.07
    Dr
    -0.07
    �
    -0.07
    axon
    -0.07
    POSITIVE LOGITS
     desap
    0.09
     Prostit
    0.08
     Upcoming
    0.08
     impending
    0.08
     сообщает
    0.08
     colorado
    0.08
     aproxima
    0.08
     tjejer
    0.08
     sluggish
    0.08
     ես
    0.08
    Activations Density 0.000%

    No Known Activations