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. 45196
    Prev
    Next
    INDEX
    Explanations

    RF

    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
     turf
    -0.10
     muz
    -0.09
    spers
    -0.08
     tih
    -0.08
     ork
    -0.08
    ainment
    -0.08
     Turf
    -0.08
     seks
    -0.07
    ajor
    -0.07
    ુ
    -0.07
    POSITIVE LOGITS
     주소
    0.08
     phishing
    0.08
     кому
    0.08
     גור
    0.08
     adress
    0.08
     spoof
    0.07
    (Server
    0.07
     attacking
    0.07
     attacks
    0.07
    주소
    0.07
    Activations Density 0.000%

    No Known Activations