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. 65825
    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
     abbiamo
    -0.07
     (?)
    -0.07
     bet
    -0.07
     sticky
    -0.07
     Bet
    -0.07
     samh
    -0.07
     Cert
    -0.07
    (Token
    -0.07
     Market
    -0.07
    akit
    -0.07
    POSITIVE LOGITS
    0.08
     ilu
    0.08
    fot
    0.08
     कदम
    0.08
    频
    0.08
    îm
    0.08
     phân
    0.08
     correr
    0.08
    ’ll
    0.07
    abra
    0.07
    Activations Density 0.000%

    No Known Activations