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. 76368
    Prev
    Next
    INDEX
    Explanations

    оформление/registration

    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
     tragedies
    -0.08
    apatan
    -0.08
     grupper
    -0.08
    수가
    -0.08
     γεγον
    -0.08
     Theatre
    -0.08
     выступ
    -0.08
    ποί
    -0.08
    οί
    -0.07
    LEG
    -0.07
    POSITIVE LOGITS
    手续
    0.18
    办理
    0.14
     paperwork
    0.13
     اللازمة
    0.11
    过程
    0.11
     burocr
    0.10
    流程
    0.10
     démarches
    0.10
    过程中
    0.10
     visas
    0.09
    Activations Density 0.050%

    No Known Activations