© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102937
    Prev
    Next
    INDEX
    Explanations

    possible

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eigent
    -0.08
     Attached
    -0.08
     pixels
    -0.08
    Tpl
    -0.08
    Eval
    -0.08
    Zeros
    -0.08
    roots
    -0.08
    }px
    -0.08
    csv
    -0.08
     eval
    -0.07
    POSITIVE LOGITS
     possible
    0.17
     posibles
    0.14
     possibile
    0.14
     possíveis
    0.13
     mumkin
    0.13
     mogelijke
    0.13
     возмож
    0.13
     possível
    0.13
    Possible
    0.13
     arrangements
    0.13
    Activations Density 0.023%

    No Known Activations