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. 49057
    Prev
    Next
    INDEX
    Explanations

    find

    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
     leve
    -0.08
    -cache
    -0.08
    -stick
    -0.08
    .content
    -0.08
     vandal
    -0.07
    724
    -0.07
    -packed
    -0.07
     nuestras
    -0.07
    -0.07
     nephew
    -0.07
    POSITIVE LOGITS
    restrict
    0.10
     диапаз
    0.09
     restrictive
    0.09
     bounded
    0.09
     restricting
    0.09
    范围
    0.09
     constraints
    0.08
     stringent
    0.08
     restrict
    0.08
    .Range
    0.08
    Activations Density 0.053%

    No Known Activations