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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 91125
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     Bend
    -0.08
     bend
    -0.08
     أنفس
    -0.07
     sæ
    -0.07
     ئە
    -0.07
     bil
    -0.07
     gestor
    -0.07
     Herr
    -0.07
     nach
    -0.07
     Emp
    -0.07
    POSITIVE LOGITS
    lungen
    0.08
     بودن
    0.08
     noh
    0.08
     Humanities
    0.08
    (remote
    0.08
     Ganz
    0.08
     Mith
    0.08
    —as
    0.08
    Unnamed
    0.08
    pipe
    0.07
    Activations Density 0.228%

    No Known Activations