© 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. 102829
    Prev
    Next
    INDEX
    Explanations

    Code documentation and comments

    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
     हमारी
    -0.09
     our
    -0.08
     өз
    -0.08
     आपकी
    -0.08
     अपनी
    -0.08
     iyong
    -0.08
    ，美国
    -0.08
     latest
    -0.08
     призн
    -0.08
     your
    -0.08
    POSITIVE LOGITS
    Purpose
    0.14
     Purpose
    0.13
     vermutlich
    0.13
     probablement
    0.12
    Overall
    0.12
     purpose
    0.12
     likely
    0.12
     উদ্দেশ
    0.12
     commented
    0.12
     waarschijnlijk
    0.12
    Activations Density 0.033%

    No Known Activations