© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54697
    Prev
    Next
    INDEX
    Explanations

    sexuality

    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
     tranquille
    -0.08
     gcc
    -0.08
     आदेश
    -0.08
    clerc
    -0.08
    衛
    -0.08
    gcc
    -0.08
    registre
    -0.07
    ='./
    -0.07
     collars
    -0.07
    킨
    -0.07
    POSITIVE LOGITS
    传播
    0.08
     person
    0.08
     Operational
    0.08
     affin
    0.08
     operational
    0.08
     alright
    0.08
     fung
    0.08
    ್ಯ
    0.08
     inbound
    0.08
     bisexual
    0.08
    Activations Density 0.002%

    No Known Activations