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. 65121
    Prev
    Next
    INDEX
    Explanations

    the

    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
    臭
    -0.08
    flora
    -0.08
    imentu
    -0.08
    onsa
    -0.07
     ಪು
    -0.07
    ág
    -0.07
    東
    -0.07
    uitive
    -0.07
    utha
    -0.07
    aminen
    -0.07
    POSITIVE LOGITS
     denomin
    0.09
     numerator
    0.08
     quot
    0.08
    整数
    0.08
     irres
    0.08
     candidatura
    0.07
     quadratic
    0.07
     afaka
    0.07
     denominator
    0.07
     verhind
    0.07
    Activations Density 0.032%

    No Known Activations