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. 90274
    Prev
    Next
    INDEX
    Explanations

    compost

    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
    ضي
    -0.08
     trademark
    -0.08
     commercials
    -0.07
     constellation
    -0.07
    astr
    -0.07
    ∀
    -0.07
    greater
    -0.07
    كل
    -0.07
     salient
    -0.07
    .Broadcast
    -0.07
    POSITIVE LOGITS
     blended
    0.09
     Chapman
    0.09
     Compost
    0.08
     blends
    0.08
     moss
    0.08
     compost
    0.08
     veld
    0.08
     chic
    0.08
     advisable
    0.08
     Moss
    0.08
    Activations Density 0.003%

    No Known Activations