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. 77120
    Prev
    Next
    INDEX
    Explanations

    Medical/cosmetic treatments

    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
    ariya
    -0.10
     garden
    -0.08
    ’est
    -0.08
     spinach
    -0.08
    /general
    -0.08
     unc
    -0.08
    brecht
    -0.08
    unc
    -0.07
     happiness
    -0.07
    irea
    -0.07
    POSITIVE LOGITS
    次数
    0.12
     серия
    0.11
     repeated
    0.11
     серии
    0.11
     séances
    0.11
     sessões
    0.10
     sessions
    0.10
    周期
    0.10
     regelmäß
    0.10
    系列
    0.10
    Activations Density 0.016%

    No Known Activations