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. 77513
    Prev
    Next
    INDEX
    Explanations

    to

    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
     validation
    -0.08
    业务
    -0.08
    ancin
    -0.07
     Med
    -0.07
     rhythms
    -0.07
     stereotypes
    -0.07
     estil
    -0.07
    ியும்
    -0.07
     nisso
    -0.07
    主要
    -0.07
    POSITIVE LOGITS
     utterly
    0.09
     moved
    0.09
     lime
    0.09
    lington
    0.09
     bort
    0.09
     окно
    0.08
     오른
    0.08
     hul
    0.08
     ↵    ↵
    0.08
     voila
    0.08
    Activations Density 0.014%

    No Known Activations