© 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. 11-RESID-POST-AA
    11. 44906
    Prev
    Next
    INDEX
    Explanations

    piece

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anthrop
    -0.07
     огром
    -0.07
     alf
    -0.07
    Bet
    -0.07
    Anth
    -0.07
     bead
    -0.07
    ド
    -0.07
     protocolo
    -0.07
     onboard
    -0.07
    Grab
    -0.07
    POSITIVE LOGITS
    -ci
    0.08
    -separated
    0.08
     Universities
    0.08
    �
    0.07
    .Course
    0.07
    별
    0.07
     Input
    0.07
    -là
    0.07
     Savior
    0.07
     Colleges
    0.07
    Activations Density 0.005%

    No Known Activations