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. 12721
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ্বর
    -0.08
    отруд
    -0.08
    ograd
    -0.08
     support
    -0.08
    _cor
    -0.07
    shaus
    -0.07
     Recogn
    -0.07
     virkelig
    -0.07
     stationed
    -0.07
     aal
    -0.07
    POSITIVE LOGITS
     избег
    0.09
     except
    0.09
    except
    0.09
     mutta
    0.09
     avoiding
    0.08
     уда
    0.08
    Avoid
    0.08
    avo
    0.08
     escaping
    0.08
    MMM
    0.08
    Activations Density 0.014%

    No Known Activations