© 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. 102821
    Prev
    Next
    INDEX
    Explanations

    modal verbs

    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
     معين
    -0.08
     měli
    -0.08
     ಇದು
    -0.08
     designing
    -0.08
    -write
    -0.07
     representar
    -0.07
     ???
    -0.07
    ?),
    -0.07
    ???
    -0.07
     représente
    -0.07
    POSITIVE LOGITS
     includes
    0.14
     mentions
    0.14
     omvat
    0.13
    包括
    0.13
     umfasst
    0.13
     discusses
    0.12
     culmin
    0.12
     beinhaltet
    0.12
     شامل
    0.12
     explores
    0.12
    Activations Density 0.031%

    No Known Activations