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. 117541
    Prev
    Next
    INDEX
    Explanations

    toward

    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
     output
    -0.08
    Jud
    -0.08
    ight
    -0.08
     Which
    -0.07
    Automation
    -0.07
    Which
    -0.07
     predefined
    -0.07
     Answer
    -0.07
     payoff
    -0.07
    .output
    -0.07
    POSITIVE LOGITS
     atributos
    0.09
    idité
    0.08
    ங்கள்
    0.08
    (frm
    0.08
     Eigenschaften
    0.08
     xəb
    0.08
    <TKey
    0.08
     꿈
    0.08
     xir
    0.08
     نخ
    0.08
    Activations Density 0.001%

    No Known Activations