© 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. 23-RESID-POST-AA
    11. 48240
    Prev
    Next
    INDEX
    Explanations

    math equations

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     schema
    -0.09
     Schema
    -0.09
     eaux
    -0.08
    lumot
    -0.08
     עסק
    -0.08
    (schema
    -0.08
    .schema
    -0.08
    ��
    -0.08
    _du
    -0.08
     国
    -0.08
    POSITIVE LOGITS
     tr
    0.25
     trig
    0.22
    Tr
    0.21
     Tr
    0.20
    tr
    0.18
    	tr
    0.16
    Trig
    0.16
    -tr
    0.16
     trigo
    0.16
    _tr
    0.16
    Activations Density 0.040%

    No Known Activations