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. 9233
    Prev
    Next
    INDEX
    Explanations

    Medical follow-up

    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
     género
    -0.08
     brute
    -0.08
     Developers
    -0.08
     reversible
    -0.08
     bounded
    -0.08
     developers
    -0.08
    cred
    -0.07
    Phrase
    -0.07
     profanity
    -0.07
     기업
    -0.07
    POSITIVE LOGITS
     outpatient
    0.13
     acompanhamento
    0.12
     консульта
    0.12
     monitoring
    0.11
     counseling
    0.11
    预约
    0.11
     visits
    0.11
    Monitoring
    0.11
     консульт
    0.11
     Betreuung
    0.11
    Activations Density 0.016%

    No Known Activations