© 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. 96929
    Prev
    Next
    INDEX
    Explanations

    ví

    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
    UNDAY
    -0.09
    illion
    -0.08
     medan
    -0.08
    izers
    -0.08
     unfolded
    -0.08
     academ
    -0.08
     kaki
    -0.08
    izing
    -0.08
     camouflage
    -0.08
     과
    -0.08
    POSITIVE LOGITS
    deo
    0.15
    deos
    0.15
    டியோ
    0.14
    ഡിയോ
    0.14
    డియో
    0.13
    ڈیو
    0.13
    ڊيو
    0.13
    ಡಿಯ
    0.12
    디오
    0.12
     dụ
    0.12
    Activations Density 0.001%

    No Known Activations