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. 52893
    Prev
    Next
    INDEX
    Explanations

    percent

    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
     DEL
    -0.08
     Сем
    -0.07
    ్యూ�
    -0.07
     imponer
    -0.07
    -ROM
    -0.07
    257
    -0.07
     msm
    -0.07
     Proposition
    -0.07
     dels
    -0.07
     Demi
    -0.07
    POSITIVE LOGITS
    thest
    0.08
     throm
    0.08
    quis
    0.08
    ri
    0.08
     మంది
    0.08
    alle
    0.07
     comput
    0.07
    919
    0.07
    centric
    0.07
    938
    0.07
    Activations Density 0.014%

    No Known Activations