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. 91050
    Prev
    Next
    INDEX
    Explanations

    set

    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
     triun
    -0.08
     Reyes
    -0.08
     bä
    -0.08
    _OBJ
    -0.08
    _objs
    -0.08
     batter
    -0.08
     horseback
    -0.08
    ámara
    -0.07
    yste
    -0.07
    ,obj
    -0.07
    POSITIVE LOGITS
     estabelecer
    0.08
     Establish
    0.08
     establish
    0.08
    tmp
    0.08
     monat
    0.07
    -dismissible
    0.07
     refinery
    0.07
     établ
    0.07
     engine
    0.07
    industry
    0.07
    Activations Density 0.001%

    No Known Activations