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. 98655
    Prev
    Next
    INDEX
    Explanations

    .

    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
     c
    -0.08
     unteren
    -0.08
     Dy
    -0.08
    .arr
    -0.07
     Mala
    -0.07
    3
    -0.07
     troisième
    -0.07
    Tracks
    -0.07
     Leap
    -0.07
     gada
    -0.07
    POSITIVE LOGITS
    gebung
    0.08
    926
    0.07
     sjón
    0.07
    BU
    0.07
    987
    0.07
    _geo
    0.07
     siph
    0.07
    召开
    0.07
     gamut
    0.07
    macht
    0.07
    Activations Density 0.005%

    No Known Activations