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. 67637
    Prev
    Next
    INDEX
    Explanations

    needs and likes

    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
    tho
    -0.08
    .th
    -0.08
    Jh
    -0.07
    езап
    -0.07
     aliquam
    -0.07
     destroying
    -0.07
     ultrasonic
    -0.07
    _we
    -0.07
    (th
    -0.07
     overrides
    -0.07
    POSITIVE LOGITS
     excepto
    0.13
     одинаков
    0.13
     behalve
    0.13
     except
    0.12
    都有
    0.12
     đều
    0.12
     sauf
    0.11
     تقريب
    0.11
    except
    0.11
     সবাই
    0.11
    Activations Density 0.171%

    No Known Activations