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. 98290
    Prev
    Next
    INDEX
    Explanations

    O

    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
    F
    -0.10
     F
    -0.09
    Fs
    -0.09
    f
    -0.09
    G
    -0.08
    U
    -0.08
    Fx
    -0.08
    ,F
    -0.08
    ff
    -0.08
    hv
    -0.08
    POSITIVE LOGITS
    OKIE
    0.11
    OGLE
    0.10
    I
    0.09
    OND
    0.09
    LOUR
    0.08
    LOY
    0.08
    LOYEE
    0.08
    URES
    0.08
    LOAT
    0.08
    जे
    0.08
    Activations Density 0.007%

    No Known Activations