© 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. 102932
    Prev
    Next
    INDEX
    Explanations

    Code parameters with values

    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
     adoption
    -0.08
     keinerlei
    -0.08
     genü
    -0.08
     FALSE
    -0.07
     vielleicht
    -0.07
     any
    -0.07
     following
    -0.07
     nincs
    -0.07
    ALSE
    -0.07
     concom
    -0.07
    POSITIVE LOGITS
     yönet
    0.08
     בנושא
    0.08
     Yönet
    0.08
     관리
    0.08
     mää
    0.08
    Managing
    0.08
    .manage
    0.08
     განს
    0.07
     사진
    0.07
    Manage
    0.07
    Activations Density 0.000%

    No Known Activations