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. 131039
    Prev
    Next
    INDEX
    Explanations

    C

    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
    ahrt
    -0.08
    atá
    -0.08
     overlap
    -0.08
     Außen
    -0.08
    ow
    -0.07
    _overlap
    -0.07
     overl
    -0.07
     hangen
    -0.07
    ayd
    -0.07
     ownership
    -0.07
    POSITIVE LOGITS
    ech
    0.10
    zas
    0.10
    zego
    0.10
    mentar
    0.10
    ies
    0.09
    ez
    0.09
    zuje
    0.09
    zeka
    0.09
    ios
    0.08
    iebie
    0.08
    Activations Density 0.000%

    No Known Activations