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. 30762
    Prev
    Next
    INDEX
    Explanations

    Social media body image concerns

    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
    ência
    -0.08
     Nullable
    -0.08
    .Sem
    -0.08
    Zombie
    -0.07
     Supremo
    -0.07
     semiconductor
    -0.07
    Insight
    -0.07
    Newton
    -0.07
    -low
    -0.07
    QI
    -0.07
    POSITIVE LOGITS
     चिं
    0.11
    患
    0.10
     fears
    0.10
     मत
    0.09
     anxiety
    0.09
     dissatisfaction
    0.09
     dissatisfied
    0.09
     भाव
    0.08
     fearful
    0.08
     atte
    0.08
    Activations Density 0.004%

    No Known Activations