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. 53319
    Prev
    Next
    INDEX
    Explanations

    continuity

    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
     prominently
    -0.09
     MY
    -0.09
     প্রকাশ
    -0.08
     Blatt
    -0.08
    ็ม
    -0.08
     LINK
    -0.08
    -প
    -0.08
     Nus
    -0.07
    .inf
    -0.07
    .pag
    -0.07
    POSITIVE LOGITS
     continuity
    0.09
     discontinu
    0.08
     seamless
    0.08
     improve
    0.08
    indrome
    0.08
    _ajax
    0.08
    except
    0.08
    Impro
    0.07
     улучш
    0.07
     discontinue
    0.07
    Activations Density 0.005%

    No Known Activations