© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2680
    Prev
    Next
    INDEX
    Explanations

    ou

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sonore
    -0.08
    .Destroy
    -0.08
    �
    -0.08
     المسؤول
    -0.07
     mindset
    -0.07
    apsible
    -0.07
    ア
    -0.07
    .destroy
    -0.07
    schirm
    -0.07
     SOB
    -0.07
    POSITIVE LOGITS
    ъп
    0.08
     repartir
    0.08
     Trek
    0.08
     Ivy
    0.08
    Her
    0.08
    nef
    0.08
     Herd
    0.07
    Rolling
    0.07
     Girl
    0.07
     hosped
    0.07
    Activations Density 0.000%

    No Known Activations