Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 120476
    Prev
    Next
    INDEX
    Explanations

    directions/screenplay

    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
    oids
    -0.08
    ocu
    -0.08
     chứng
    -0.08
     ισ
    -0.07
    ajien
    -0.07
     fomentar
    -0.07
     democr
    -0.07
    oka
    -0.07
     yet
    -0.07
    oci
    -0.07
    POSITIVE LOGITS
     Neste
    0.09
     artis
    0.08
     यूर
    0.08
     Croix
    0.08
    (Point
    0.07
     scor
    0.07
     给
    0.07
     alteration
    0.07
    (["
    0.07
     Torrent
    0.07
    Activations Density 0.000%

    No Known Activations