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. 55867
    Prev
    Next
    INDEX
    Explanations

    architecture

    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
    ublished
    -0.09
     apologized
    -0.08
    aware
    -0.08
     apag
    -0.08
     urged
    -0.08
     asked
    -0.08
     mph
    -0.07
     dní
    -0.07
     vins
    -0.07
     acknowledged
    -0.07
    POSITIVE LOGITS
     UNESCO
    0.08
     здания
    0.08
     specimen
    0.08
     сооруж
    0.08
     Headquarters
    0.08
     учреждения
    0.08
    用途
    0.08
     structures
    0.08
     อาคาร
    0.08
     headquarters
    0.08
    Activations Density 0.069%

    No Known Activations