Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130960
    Prev
    Next
    INDEX
    Explanations

    ans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ाब
    -0.08
    Evidence
    -0.08
    Delivered
    -0.08
    ાબ
    -0.07
    respect
    -0.07
    Abilities
    -0.07
    Respect
    -0.07
    habil
    -0.07
    ebil
    -0.07
    mens
    -0.07
    POSITIVE LOGITS
    ätze
    0.13
    wear
    0.12
    icht
    0.12
    atz
    0.12
    ichts
    0.11
    wwer
    0.11
    ichten
    0.11
    IBLE
    0.10
    etzung
    0.10
    etze
    0.10
    Activations Density 0.001%

    No Known Activations