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. 119380
    Prev
    Next
    INDEX
    Explanations

    or

    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
     조금
    -0.08
    UIView
    -0.08
     etiam
    -0.08
     快
    -0.08
     sympa
    -0.08
     하고
    -0.08
     plutôt
    -0.07
     Cuban
    -0.07
     이렇게
    -0.07
    ними
    -0.07
    POSITIVE LOGITS
     سوى
    0.11
     siquiera
    0.10
     unless
    0.09
    except
    0.09
     except
    0.09
     excessive
    0.09
    unless
    0.08
    Except
    0.08
     edes
    0.08
     nor
    0.08
    Activations Density 0.064%

    No Known Activations