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. 76509
    Prev
    Next
    INDEX
    Explanations

    personal opinions/descriptions

    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
     అనంత
    -0.09
     centaines
    -0.08
     dozens
    -0.08
     milliers
    -0.08
     sichern
    -0.08
    終了
    -0.07
     제외
    -0.07
    月至
    -0.07
     vek
    -0.07
    炉
    -0.07
    POSITIVE LOGITS
     penchant
    0.18
     tendencies
    0.14
     procl
    0.13
     tendency
    0.13
    喜欢
    0.13
     склон
    0.12
     любит
    0.12
     propensity
    0.12
     knack
    0.12
     procrast
    0.11
    Activations Density 0.246%

    No Known Activations