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. 58388
    Prev
    Next
    INDEX
    Explanations

    yellow

    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
     Böl
    -0.09
    holy
    -0.08
     susp
    -0.08
     holy
    -0.08
    Holy
    -0.08
     sanct
    -0.08
    Hol
    -0.07
    Nah
    -0.07
     ganar
    -0.07
     scissors
    -0.07
    POSITIVE LOGITS
     pudd
    0.08
    plib
    0.08
     bruke
    0.08
     faded
    0.08
    rvore
    0.07
     Failure
    0.07
    .Light
    0.07
     käyttää
    0.07
     Indicators
    0.07
     backpage
    0.07
    Activations Density 0.003%

    No Known Activations