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. 130867
    Prev
    Next
    INDEX
    Explanations

    mention

    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
     (=
    -0.10
     shown
    -0.10
     represented
    -0.10
    shown
    -0.09
     says
    -0.09
    ?).
    -0.09
     huh
    -0.09
    Rather
    -0.09
     described
    -0.09
    ?),
    -0.09
    POSITIVE LOGITS
     how
    0.22
     כיצד
    0.19
     hvernig
    0.18
     the
    0.18
    如何
    0.17
     كيف
    0.17
     hvordan
    0.16
     cómo
    0.16
     كيفية
    0.16
     about
    0.16
    Activations Density 0.104%

    No Known Activations