© 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. 64921
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Select
    -0.08
    ihl
    -0.08
     عملکرد
    -0.08
     társ
    -0.08
    ocal
    -0.07
     tilt
    -0.07
     eş
    -0.07
     mű
    -0.07
     Shannon
    -0.07
     ters
    -0.07
    POSITIVE LOGITS
     размещ
    0.09
    位置
    0.09
     принадлеж
    0.08
     lying
    0.08
     geplaatst
    0.08
    _positions
    0.08
     located
    0.08
     располож
    0.08
     positioned
    0.08
     situated
    0.08
    Activations Density 0.041%

    No Known Activations