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. 44425
    Prev
    Next
    INDEX
    Explanations

    numerical calculations

    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
    क्ति
    -0.08
    ક્ત
    -0.08
    ંતુ
    -0.08
    ക്ത
    -0.07
     supervising
    -0.07
     oversee
    -0.07
    aktu
    -0.07
    াক্ত
    -0.07
    uktur
    -0.07
    ective
    -0.07
    POSITIVE LOGITS
    Exact
    0.09
     exact
    0.09
     Exact
    0.09
     procent
    0.08
     ligeramente
    0.08
     Slight
    0.08
     légèrement
    0.08
    _exact
    0.08
    exact
    0.08
     sest
    0.08
    Activations Density 0.136%

    No Known Activations