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. 30783
    Prev
    Next
    INDEX
    Explanations

    recall

    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
    गो
    -0.09
    	delay
    -0.08
     delays
    -0.08
    (delay
    -0.08
     shipment
    -0.08
    (batch
    -0.08
    .googleapis
    -0.08
     gamme
    -0.08
     delay
    -0.07
     delaying
    -0.07
    POSITIVE LOGITS
     impeachment
    0.12
     deth
    0.09
     voted
    0.08
     impe
    0.08
     Construction
    0.08
     overthrow
    0.08
    thumb
    0.08
     ballon
    0.08
     revoke
    0.07
     unjust
    0.07
    Activations Density 0.019%

    No Known Activations